Update app.py

app.py

@@ -162,28 +162,12 @@ def evaluate_model(model, env):
     mean_reward, _ = evaluate_policy(model, env, n_eval_episodes=10, render=False)
     return mean_reward
 
-# Gradio interface
-def play_game():
-    env = ArkanoidEnv()
-    model = DQN.load("arkanoid_model")
-    obs = env.reset()[0]
-    done = False
-    frames = []
-    while not done:
-        action, _states = model.predict(obs, deterministic=True)
-        obs, reward, done, truncated, info = env.step(action)
-        env.render()
-        pygame.image.save(screen, "frame.png")
-        frames.append(gr.Image(value="frame.png"))
-    return frames
-
 # Real-time training function
 def train_and_play():
     env = ArkanoidEnv()
     model = DQN('MlpPolicy', env, verbose=1)
     total_timesteps = 10000
     timesteps_per_update = 1000
-    frames = []
     video_frames = []
 
     for i in range(0, total_timesteps, timesteps_per_update):
@@ -191,7 +175,6 @@ def train_and_play():
         obs = env.reset()[0]
         done = False
         truncated = False
-        episode_frames = []
         while not done and not truncated:
             action, _states = model.predict(obs, deterministic=True)
             obs, reward, done, truncated, info = env.step(action)
@@ -200,9 +183,6 @@ def train_and_play():
             frame = pygame.surfarray.array3d(pygame.display.get_surface())
             frame = cv2.cvtColor(frame, cv2.COLOR_RGB2BGR)
             video_frames.append(frame)
-            episode_frames.append(gr.Image(value="frame.png"))
-        frames.extend(episode_frames)
-        yield frames
 
     # Save the video
     video_path = "arkanoid_training.mp4"
@@ -213,7 +193,7 @@ def train_and_play():
     video_writer.release()
 
     # Return the video path
-    return gr.Video(video_path)
+    return video_path
 
 # Main function
 def main():